國立虎尾科技大學 |

Score Distribution Analysis, Artificial Intelligence, and Player Modeling for Quantitative Game Design.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Score Distribution Analysis, Artificial Intelligence, and Player Modeling for Quantitative Game Design./
作者:	Isaksen, Aaron.
面頁冊數:	1 online resource (202 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9781369851533

Score Distribution Analysis, Artificial Intelligence, and Player Modeling for Quantitative Game Design.
Isaksen, Aaron.

Score Distribution Analysis, Artificial Intelligence, and Player Modeling for Quantitative Game Design. - 1 online resource (202 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)--Polytechnic Institute of New York University, 2017.

Includes bibliographical references

We use score distribution data analysis, artificial intelligence, and player modeling to better understand games and game design using quantitative techniques, for studying the characteristics of games, and to explore the space of possible games. Score distributions model the probability a score will be achieved by a player; we model and visualize such probabilities using survival analysis, mean score, closeness, high score analysis, and other metrics. We apply artificial intelligence techniques to quantitative game design using tree search, genetic programming, optimization, procedural content generation, and Q-value modeling, focusing on general solutions. We analyze score data collected from human game play, in addition to simulated game play for scalable, repeatable, and controlled data experiments. We employ novel player modeling techniques to more accurately simulate human motor skill, timing accuracy, aiming dexterity, strategic thinking, inequity aversion, and learning effects. Quantitative analysis of simulated and real score data is used to explore various characteristics of games, including human-playable heuristics, game difficulty, score inequity, game balance, length of playtime, randomness, luck, skill, dexterity, and strategy required. We also explore game space to find new game variants using Monte Carlo simulation, computational creativity, sampling, mathematical modeling, and evolutionary search. This thesis contributes to the state of the art in several areas, including the first time that survival analysis has been applied to automated game design, the first quantitative calculation of difficulty curves, proving the probability of setting new high scores, and measuring the interaction of strategy and dexterity in games.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369851533Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Score Distribution Analysis, Artificial Intelligence, and Player Modeling for Quantitative Game Design.
LDR:02973ntm a2200325K 4500 001 915306
005 20180727125212.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369851533
035 $a (MiAaPQ)AAI10280433
035 $a (MiAaPQ)poly:10353
035 $a AAI10280433
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Isaksen, Aaron. $3 1188623
245 1 0 $a Score Distribution Analysis, Artificial Intelligence, and Player Modeling for Quantitative Game Design.
264 0 $c 2017
300 $a 1 online resource (202 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Andy Nealen.
502 $a Thesis (Ph.D.)--Polytechnic Institute of New York University, 2017.
504 $a Includes bibliographical references
520 $a We use score distribution data analysis, artificial intelligence, and player modeling to better understand games and game design using quantitative techniques, for studying the characteristics of games, and to explore the space of possible games. Score distributions model the probability a score will be achieved by a player; we model and visualize such probabilities using survival analysis, mean score, closeness, high score analysis, and other metrics. We apply artificial intelligence techniques to quantitative game design using tree search, genetic programming, optimization, procedural content generation, and Q-value modeling, focusing on general solutions. We analyze score data collected from human game play, in addition to simulated game play for scalable, repeatable, and controlled data experiments. We employ novel player modeling techniques to more accurately simulate human motor skill, timing accuracy, aiming dexterity, strategic thinking, inequity aversion, and learning effects. Quantitative analysis of simulated and real score data is used to explore various characteristics of games, including human-playable heuristics, game difficulty, score inequity, game balance, length of playtime, randomness, luck, skill, dexterity, and strategy required. We also explore game space to find new game variants using Monte Carlo simulation, computational creativity, sampling, mathematical modeling, and evolutionary search. This thesis contributes to the state of the art in several areas, including the first time that survival analysis has been applied to automated game design, the first quantitative calculation of difficulty curves, proving the probability of setting new high scores, and measuring the interaction of strategy and dexterity in games.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Polytechnic Institute of New York University. $b Computer Science and Engineering. $3 1188624
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10280433 $z click for full text (PQDT)